Actions16
Overview
The "Voice Changer" operation within the Speech resource of this node allows users to transform an existing audio file by applying a different voice model. This is useful for scenarios such as creating voiceovers with different character voices, modifying recorded audio for privacy or entertainment, or generating customized audio content with specific voice characteristics.
For example, you could input a podcast recording and change the speaker's voice to sound like a celebrity or a fictional character, or convert a narration into a different accent or style without re-recording.
Properties
| Name | Meaning |
|---|---|
| Binary Input Field | The name of the binary property in the input data that contains the audio file to be transformed by the voice changer. |
| Voice ID | The identifier of the target voice to apply to the input audio. Can be selected from a searchable list of available voices or entered manually by ID. |
| Model Name or ID | The specific voice model to use for the transformation. Selectable from a list or specified by ID. |
| Stability | A number between 0 and 1 defining how stable the voice output should be (e.g., less variation). Default is 0.5. |
| Similarity Boost | A number between 0 and 1 controlling how closely the output voice matches the target voice. Default is 0.75. |
| Style | A number between 0 and 1 to exaggerate the voice style. Default is 0. |
| Speaker Boost | Boolean flag to activate speaker boost feature. Default is false. |
| Seed | A numeric seed value (0 to 4294967295) to make the voice transformation deterministic; same seed and input produce the same output. Default is 0. |
| Remove Background Noise | Boolean option to remove background noise from the input audio before processing. Default is false. |
| Streaming Latency | Numeric value (0-4) to optimize streaming latency at some cost to quality. Values range from 0 (no optimization) to 4 (max optimization with text normalization off). Default is 0. |
| Output Format | The audio format of the output file. Options include various MP3 and PCM formats, and μ-Law encoding. Default is MP3 (44.1kHz, 128kbps). |
| Binary Name | Optional string to rename the output binary property. Default is "data". |
| File Name | Optional string to specify the output file name. Default is "voice". |
| Enable Logging | Boolean to enable or disable logging. When disabled, zero retention mode is activated (history features unavailable). Default is true. |
Output
The node outputs the transformed audio as binary data under a binary property (default named "data", but can be renamed via "Binary Name"). The binary data represents the audio file encoded in the selected output format (e.g., MP3 or PCM). The output JSON may also contain metadata about the request or response depending on configuration, but primarily the focus is on the binary audio content.
Dependencies
- Requires an API key credential for authentication with the external ElevenLabs API service.
- Network access to the ElevenLabs API endpoint (
https://api.elevenlabs.io/v1). - Proper configuration of the node credentials in n8n to provide the required API key.
- The input data must contain a binary property with the audio file to be transformed.
Troubleshooting
- Missing or invalid API key: The node will fail if the API key credential is not set or invalid. Ensure the API key is correctly configured in n8n credentials.
- Invalid or missing binary input: If the specified binary input field does not exist or is empty, the node cannot process the audio. Verify the input binary property name matches the actual input data.
- Unsupported output format: Selecting an unsupported or incorrectly spelled output format may cause errors. Use only the provided options.
- Latency optimization trade-offs: Enabling higher streaming latency optimizations may degrade audio quality. Adjust the "Streaming Latency" setting accordingly.
- Voice ID or Model ID issues: Providing an invalid or non-existent voice or model ID will result in errors. Use the list selection or verify IDs carefully.
- Large audio files: Very large input audio files might cause timeouts or memory issues depending on environment limits.